DGST: a Dual-Generator Network for Text Style Transfer
arXiv:2010.14557
Abstract
We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.
Accepted by EMNLP 2020, camera ready version